Schematic representation of the confusion matrix employed for ML classification in the context of biosignature searching. Instances (planets) in the first row possess biosignatures/bioindicators, while those in the second row do not. An algorithm labels instances (planets) in the first column as potentially having biosignatures (i.e. interesting), whereas those in the second column are not considered interesting. This framework illustrates the different classification outcomes, including true positives (TP), false positives (FP), true negatives (TN), and false negatives (FN), in the search for biosignatures/bioindicators.